John P. Overington
John studied Chemistry at the University of Bath (1987), and then completed a PhD at Birkbeck College, University of London in the Department of Crystallography (1990). There he developed automated approaches to protein modelling, contributing to the development of the programs COMPOSER and MODELLER; however his major research was on sequence-structure relationships, exploring the constraints applied by the local physical environment of a residue in constraining mutational trajectory (JOY and HOMSTRAD). John then held a postdoctoral position at the Imperial Cancer Research Fund (now part of CRUK). John then joined Pfizer (1992), originally as a computational chemist, progressing to a role where he led a multidisciplinary group combining rational drug design with structural biology. During this time, John explored the reasons for target/drug attrition and the falling productivity of the pharmaceutical industry. In 2000 John moved to a start-up biotech company, Inpharmatica, where he led the development of a series of computational and data platforms to improve drug discovery; these included the medicinal chemistry database StARLite. In 2008 John was central to the transfer of this database to the EMBL-EBI, where the successor is now known as the ChEMBL. More recently, the work extended into large-scale patent informatics with the Open patent database SureChEMBL. John then joined (2015) a London-based technology company - Stratified Medical/BenevolentAI, where he continued his translational drug discovery informatics research and development activities. In this role, John was involved in development of novel data extraction and integration strategies, and integrating deep learning and other artificial intelligence approaches to drug target validation and drug optimisation. Most recently John works as CIO at the UK's Medicines Discovery Catapult, a UK non-profit organisation driving innovation and value creation in SMEs.